Diversifying Deep Ensembles: A Saliency Map Approach for Enhanced OOD Detection, Calibration, and Accuracy
Not on the map. Why?
Abstract (arXiv)
Deep ensembles are capable of achieving state-of-the-art results in classification and out-of-distribution (OOD) detection. However, their effectiveness is limited due to the homogeneity of learned patterns within ensembles. To overcome this issue, our study introduces Saliency Diversified Deep Ensemble (SDDE), a novel approach that promotes diversity among ensemble members by leveraging saliency maps. Through incorporating saliency map diversification, our method outperforms conventional ensemble techniques and improves calibration in multiple classification and OOD detection tasks. In particular, the proposed method achieves state-of-the-art OOD detection quality, calibration, and accuracy on multiple benchmarks, including CIFAR10/100 and large-scale ImageNet datasets.
Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 35 of its 46 references that are in the map. First posted on arXiv 19 May 2023.
Builds on
35 of 46 references.
References · 35
- 2015Deep Residual Learning for Image Recognitioncited by 52,096
- 2014Explaining and Harnessing Adversarial Examplescited by 7,364
- 2016Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localizationcited by 6,733
- 2016SGDR: Stochastic Gradient Descent with Warm Restartscited by 5,045
- 2017On Calibration of Modern Neural Networkscited by 4,960
- 2016Simple and Scalable Predictive Uncertainty Estimation using Deep Ensemblescited by 3,926
- 2015Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classificationcited by 3,611
- 2019Benchmarking Neural Network Robustness to Common Corruptions and Perturbationscited by 2,877
- 2015Learning Deep Features for Discriminative Localizationcited by 2,436
- 2016A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networkscited by 2,385
- 2013Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Mapscited by 2,371
- 2020WILDS: A Benchmark of in-the-Wild Distribution Shiftscited by 1,375
23 more
- 2020In Search of Lost Domain Generalizationcited by 1,054
- 2018Deep Anomaly Detection with Outlier Exposurecited by 942
- 2018Deep Visual Domain Adaptation: A Surveycited by 635
- 2022Out-of-Distribution Detection with Deep Nearest Neighborscited by 600
- 2021ReAct: Out-of-distribution Detection With Rectified Activationscited by 486
- 2019Scaling Out-of-Distribution Detection for Real-World Settingscited by 465
- 2018Deep Learning for Generic Object Detection: A Surveycited by 392
- 2020Are we done with ImageNet?cited by 333
- 2020A Metric Learning Reality Checkcited by 321
- 2021Uncertainty-Based Offline Reinforcement Learning with Diversified Q-Ensemblecited by 302
- 2022OpenOOD: Benchmarking Generalized Out-of-Distribution Detectioncited by 268
- 2019Improving Adversarial Robustness via Promoting Ensemble Diversitycited by 213
- 2020Pitfalls of In-Domain Uncertainty Estimation and Ensembling in Deep Learningcited by 210
- 2020Bayesian Neural Networks: An Introduction and Surveycited by 131
- 2021Semantically Coherent Out-of-Distribution Detectioncited by 107
- 2021Shifts: A Dataset of Real Distributional Shift Across Multiple Large-Scale Taskscited by 101
- 2022Wild-Time: A Benchmark of in-the-Wild Distribution Shift over Timecited by 90
- 2022Deep Ensembles Work, But Are They Necessary?cited by 63
- 2021DICE: Diversity in Deep Ensembles via Conditional Redundancy Adversarial Estimationcited by 48
- 2022Shifts 2.0: Extending The Dataset of Real Distributional Shiftscited by 24
- 2020Diverse Ensembles Improve Calibrationcited by 23
- 2018Diversity regularization in deep ensemblescited by 11
- 2022Confidence estimation of classification based on the distribution of the neural network output layercited by 8
Built on by
Citing papers per year: 2025: 1.
1 paper.